{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EY56VNDDUKHUEHJUVBXSME6MXF","short_pith_number":"pith:EY56VNDD","canonical_record":{"source":{"id":"2505.01539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T19:04:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fae5bba8960b6324e2df3189877d14c38180c40fadd3f7bc15f65da4aefc65b9","abstract_canon_sha256":"18dcce78b9bfafa0324afa4a94e648cbc2e4599ade60e2293d73a623722bd549"},"schema_version":"1.0"},"canonical_sha256":"263beab463a28f421d34a86f2613ccb95601f02dd3d4687f6b5cb9493833deff","source":{"kind":"arxiv","id":"2505.01539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01539","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01539v1","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01539","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_12","alias_value":"EY56VNDDUKHU","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_16","alias_value":"EY56VNDDUKHUEHJU","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_8","alias_value":"EY56VNDD","created_at":"2026-07-05T10:57:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EY56VNDDUKHUEHJUVBXSME6MXF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.01539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T19:04:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fae5bba8960b6324e2df3189877d14c38180c40fadd3f7bc15f65da4aefc65b9","abstract_canon_sha256":"18dcce78b9bfafa0324afa4a94e648cbc2e4599ade60e2293d73a623722bd549"},"schema_version":"1.0"},"canonical_sha256":"263beab463a28f421d34a86f2613ccb95601f02dd3d4687f6b5cb9493833deff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:59.711120Z","signature_b64":"GAd0seexKA0pV1KabtGqeaMquu/WiDrPMr4SUG08L4lfjwf7ZFSLixCBawbeOuC9j06bYpjhkKXTTWKWwf4mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"263beab463a28f421d34a86f2613ccb95601f02dd3d4687f6b5cb9493833deff","last_reissued_at":"2026-07-05T10:57:59.710635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:59.710635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.01539","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0JTuoiBLRbheRl+WF4eG+mbB2UW6tCyS4W1QmJj0GZ6BryOK2+LLFXcmIRI/Oyz+h0IL85XR/yW0ggUuHu7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:57:41.666296Z"},"content_sha256":"32425256d1fdde193dd5d21f209a6a38257fea44d4d76a6169f3729cd49465aa","schema_version":"1.0","event_id":"sha256:32425256d1fdde193dd5d21f209a6a38257fea44d4d76a6169f3729cd49465aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EY56VNDDUKHUEHJUVBXSME6MXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bart Verheij, Cor Steging, Silja Renooij","submitted_at":"2025-05-02T19:04:34Z","abstract_excerpt":"Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01539","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.01539/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0KnUsc91CaofEY81MHFn6rNt92prL1uG7cQicR72w5n/uBYju+S88+i1bPEnOUMvsPFx6Fet6EkFAZA865NBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:57:41.666671Z"},"content_sha256":"3dc3ec73db3be1c87fbd072a6a9790d5708135405a4c84792ea919a256b8f35d","schema_version":"1.0","event_id":"sha256:3dc3ec73db3be1c87fbd072a6a9790d5708135405a4c84792ea919a256b8f35d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EY56VNDDUKHUEHJUVBXSME6MXF/bundle.json","state_url":"https://pith.science/pith/EY56VNDDUKHUEHJUVBXSME6MXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EY56VNDDUKHUEHJUVBXSME6MXF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T17:57:41Z","links":{"resolver":"https://pith.science/pith/EY56VNDDUKHUEHJUVBXSME6MXF","bundle":"https://pith.science/pith/EY56VNDDUKHUEHJUVBXSME6MXF/bundle.json","state":"https://pith.science/pith/EY56VNDDUKHUEHJUVBXSME6MXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EY56VNDDUKHUEHJUVBXSME6MXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EY56VNDDUKHUEHJUVBXSME6MXF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"18dcce78b9bfafa0324afa4a94e648cbc2e4599ade60e2293d73a623722bd549","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T19:04:34Z","title_canon_sha256":"fae5bba8960b6324e2df3189877d14c38180c40fadd3f7bc15f65da4aefc65b9"},"schema_version":"1.0","source":{"id":"2505.01539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01539","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01539v1","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01539","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_12","alias_value":"EY56VNDDUKHU","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_16","alias_value":"EY56VNDDUKHUEHJU","created_at":"2026-07-05T10:57:59Z"},{"alias_kind":"pith_short_8","alias_value":"EY56VNDD","created_at":"2026-07-05T10:57:59Z"}],"graph_snapshots":[{"event_id":"sha256:3dc3ec73db3be1c87fbd072a6a9790d5708135405a4c84792ea919a256b8f35d","target":"graph","created_at":"2026-07-05T10:57:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.01539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the bas","authors_text":"Bart Verheij, Cor Steging, Silja Renooij","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T19:04:34Z","title":"Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01539","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:32425256d1fdde193dd5d21f209a6a38257fea44d4d76a6169f3729cd49465aa","target":"record","created_at":"2026-07-05T10:57:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"18dcce78b9bfafa0324afa4a94e648cbc2e4599ade60e2293d73a623722bd549","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T19:04:34Z","title_canon_sha256":"fae5bba8960b6324e2df3189877d14c38180c40fadd3f7bc15f65da4aefc65b9"},"schema_version":"1.0","source":{"id":"2505.01539","kind":"arxiv","version":1}},"canonical_sha256":"263beab463a28f421d34a86f2613ccb95601f02dd3d4687f6b5cb9493833deff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"263beab463a28f421d34a86f2613ccb95601f02dd3d4687f6b5cb9493833deff","first_computed_at":"2026-07-05T10:57:59.710635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:59.710635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GAd0seexKA0pV1KabtGqeaMquu/WiDrPMr4SUG08L4lfjwf7ZFSLixCBawbeOuC9j06bYpjhkKXTTWKWwf4mBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:59.711120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32425256d1fdde193dd5d21f209a6a38257fea44d4d76a6169f3729cd49465aa","sha256:3dc3ec73db3be1c87fbd072a6a9790d5708135405a4c84792ea919a256b8f35d"],"state_sha256":"079fded6cf0e3afd485671166147640a2fdc2d387843449d21f0267790c64071"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQDlml05Sm17gMA78MR5XbH+zA6TC0xif3db5kyZFGGHcfhOjPUz/ERSXv8P4d4rmdOEz56xpJmCcsd5fyruCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T17:57:41.669394Z","bundle_sha256":"88f1286213a742c8672e5c47ea11cc64de4592e1ce802af5573a8b4b41db5c10"}}